Soel Micheletti

Large-scale, interpretable gene regulatory network inference through biologically informed matrix factorization

This paper introduces Giraffe, a matrix factorization method for gene regulatory network inference that estimates signed regulatory effects, showing improved accuracy in distinguishing activating and inhibitory interactions across multiple biological contexts.

Reproducible processing of TCGA regulatory networks

The paper develops a Nextflow workflow for reproducibly inferring regulatory networks from TCGA data, showing its application to colon cancer subtypes.

Higher-order correction of persistent batch effects in correlation networks

This paper introduces COBRA, a method to correct batch effects in gene co-expression networks, showing that standard batch correction does not fully eliminate spurious co-expression associations.